theprint/CleverBoi-7B-v3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: theprint/CleverBoi-7B-v3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-06 05:05:17 +08:00
commit e09900bbe8
18 changed files with 105317 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
.gitattributes vendored Normal file
View File

@@ -0,0 +1,53 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.F16.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.BF16.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.BF16.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
unsloth.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
CleverBoi-7B-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text

3
CleverBoi-7B-v3.BF16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0bd5b9894e5d4ffc847b79d74c8e25ba8889f63f19cbcd68c0db2ebc977b9b19
size 14497337216

3
CleverBoi-7B-v3.F16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c4b56fd3486e68cca02619ef70e7528a09ed84e9157de689a81ecf96daa1a85
size 14497337216

3
CleverBoi-7B-v3.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9054f7180745d2476f219f63314ddf6dcba5d795e720a2073d419ae846b98e54
size 3522940800

3
CleverBoi-7B-v3.Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0119d2d14d532d64338e55c9207d991ca4fc15f3c98deef2225df68876137743
size 3168522112

3
CleverBoi-7B-v3.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9bbb300a59205fa74ac19f3813972cbf7a867e544333a180e9a8c2b7b5ff4865
size 4372811648

3
CleverBoi-7B-v3.Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a37d1d289f11f756b36c58a9cb2c1b828b71035db1866108d53a4f22c5ffa59e
size 4144746368

3
CleverBoi-7B-v3.Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:508c2c531078e9d0edb37ad32cd3429b0b08b1b07d07304b354f9c53e32c557e
size 5136174976

3
CleverBoi-7B-v3.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de97d9c42ff873c6acee664d1585969ff4d70f5cbf3babd5555eba40d059ea9a
size 5947248512

3
CleverBoi-7B-v3.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1280207327872ac3200354a73c998b04bd9045ddc18142d83d232adebfe0a5b0
size 7702564736

143
README.md Normal file
View File

@@ -0,0 +1,143 @@
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- theprint
- cleverboi
base_model: unsloth/mistral-7b-v0.3-bnb-4bit
datasets:
- theprint/CleverBoi-Data-20k
pipeline_tag: text-generation
model-index:
- name: CleverBoi-7B-v3
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 23.82
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-7B-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 21.94
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-7B-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 3.17
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-7B-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 2.13
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-7B-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 9.5
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-7B-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 20.76
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-7B-v3
name: Open LLM Leaderboard
---
<img src="https://huggingface.co/theprint/CleverBoi-Gemma-2-9B/resolve/main/cleverboi.png"/>
# CleverBoi
The CleverBoi series is based on models that have been fine tuned on a collection of data sets that emphasize logic, inference, math and coding, also known as the CleverBoi data set.
This model has been fine tuned for 1 epoch on the CleverBoi-Data-20k data set.
# Uploaded model
- **Developed by:** theprint
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-v0.3-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_theprint__CleverBoi-7B-v3)
| Metric |Value|
|-------------------|----:|
|Avg. |13.55|
|IFEval (0-Shot) |23.82|
|BBH (3-Shot) |21.94|
|MATH Lvl 5 (4-Shot)| 3.17|
|GPQA (0-shot) | 2.13|
|MuSR (0-shot) | 9.50|
|MMLU-PRO (5-shot) |20.76|

34
adapter_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"o_proj",
"v_proj",
"up_proj",
"down_proj",
"gate_proj",
"k_proj",
"q_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}

3
adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00e312836edd5ce1b3c3e8b555d42f7e72211189b96c96bbd5f9e0c0510a0549
size 167832240

44
config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"_name_or_path": "theprint/CleverBoi-7B-v3",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 770,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"unsloth_version": "2024.9",
"use_cache": true,
"vocab_size": 32768
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[control_768]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

98793
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
size 587404

6187
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff